Code agents

Elyra extension for Laravel AI SDK -- agents, sub-agents, tools, structured output, embeddings, and more

Track and analyze AI coding assistant usage across Claude Code, Codex, and more

Coze Coding Dev SDK - 优雅的多功能 AI SDK，支持图片生成、视频生成、语音合成、语音识别、大语言模型和联网搜索

Multi-agent AI code review for git -- parallel agents with confidence scoring

PRIDES methodology multi-agent AI team — 21 specialized agents for the full development lifecycle

Multi-agent coordination CLI for coding agents sharing a local repository

Self-improving multi-agent orchestration that takes you from build → CI/CD → deploy. Interactive setup wizard, pluggable AI providers, agent swarms in git worktrees.

TypeScript SDK for AgentDrive — cross-agent artifact workspace with provenance, semantic recall, and portable storage.

Generate short, useful AGENTS.md files without repeating what the repo already says.

Local agent manager/worker conveyor control plane for Codex sessions.

Intercept and log AI coding agent <-> API traffic for prompt-architecture analysis.

A safety layer that lets developers use AI coding agents at work without triggering security alerts

Multi-agent framework with persistent expert sessions and context isolation — MCP server for Claude Code

CLI + TUI for viewing Claude Code usage statistics from local session files

Claude Code hook that reads assistant messages aloud via a local TTS engine

Shell LLM client control plane for semcod/coru automation.

Monty-backed code-interpreter middleware for LangChain agents

LangChain tools for Mapsi geospatial APIs — geocoding, routing, isochrone, places

Meris — model-agnostic coding agent with a per-project agent harness (.meris/)

Python bindings for newt-agent — agentic coder runtime (newt-core, newt-tools, newt-coder, newt-eval, newt-inference, newt-acp-worker, newt-mcp-server submodules)

Search as Code (SaC) — agentic search orchestration using LLMs

Frictionless Salesforce Agent Skill for Codex, Claude Code, and GitHub Copilot.

React Native SDK for nxtlinq AI Agent — custom UI hooks and platform ports

Mesh terminal agent CLI — token-efficient coding agent with a shared LLM gateway.

Make coding agents stronger engineering partners for reviews, implementation planning, and system design.

Natural Language Shell Agent — speak intent, get goals done

Open-source Agent SDK. Runs the full agent loop in-process — no local CLI required. Deploy anywhere: cloud, serverless, Docker, CI/CD.

TheClawBay provider extension for Pi Coding Agent - access GPT-5, Codex, Claude, Gemini, DeepSeek, open-weight, and image models

Local-first AI workspace for knowledge graphs, AI pipelines, and multi-agent coding workflows.

Multi-agent workflow engine powered by opencode SDK

Toolkit for automating agentic automations

Catch silent failures in your AI agents. TypeScript SDK for Pisama, the failure detector for vibe-coded agents (Cursor, Claude Code, LangGraph, Vercel AI SDK).

CLI that scores how ready a repo is for AI coding agents (Claude Code, Cursor, Copilot, Codex)

Track the cost, usage, and ROI of your AI coding agents across every tool.

Local stdio MCP server exposing unified Claude chat history (claude.ai export + Claude Code sessions) as ranked, scoped, structured search.

Context compression for Claude Code — reduces tokens via PreToolUse hooks

Local dictation backend for Claude Code (macOS, Apple Silicon) — on-device Whisper, "Hey Claude" wake word, @-file tagging, voice daemon.

Dipeen Agent — the teammate worker CLI. Joins a Dipeen workspace, pulls only commands it has the capabilities for, runs your local agent (Claude / Codex / OMO / Gemini) with your own keys, and returns evidence.

Say "Hey Claude" and dispatch a Claude Code background agent — a fully local, on-device voice wake word for your Mac.

Policy-as-code guardrail enforcement for enterprise LLM applications

Seren: A Self-Refining Decoder-Only LLM with GQA, RoPE, Flash Attention, and a novel two-pass self-refinement mechanism.

Real-time terminal monitor for Claude Code token usage — with a clean centered dashboard, keyword analytics, and a one-line installer

FREE Terminal AI Agent - agent mode with tool calling. Powered by DigitalOcean.

Markdown-native AI agent orchestrator. Write tasks in a kanban board, agents do the work.

Lightweight sub-agents for pi — spawn specialized agents with isolated sessions, tools, and models.

Pluggable adapter seam for supervising whatever actually runs an agent — the Claude Agent SDK, OpenAI Agents, the Vercel AI SDK, a plain subprocess, and more. Lets a host swap agent runtimes without hardcoding any framework into its dev loop.

MeerAI - Dive deep into your code. An open-source, local-first AI CLI for developers.

Margin Call MCP server — lets Claude Code (or any MCP-compatible agent) run an autonomous AGENT DESK on the Wall Street trading game. Per-desk MCP API keys map to dedicated CDP server wallets; tools cover read state, hire/fund/configure traders, create/cl

Olly – Autonomous AI coding agent. Multi-step reasoning, file editing, shell execution, memory, skills & 15+ AI providers including TokenLB.

Claude Code adversarial multi-agent workflows — 11 slash commands covering the full software lifecycle

A terminal-native multi-agent development system where selected coding and architecture agents co-develop through council, synthesis, implementation, review, and validation loops.

Transparent feedback compression middleware for LLM coding agents.

Read-only Inspector and evidence viewer package for AgentLedger

Framework-agnostic tool library for software architecture analysis

Lightweight self-hosted Telegram manager for Claude Code CLI

Halo adapter for Claude on two runtimes (Python): the Agent SDK (install_halo — a PostToolUse encode hook + a single in-process halo_fetch MCP tool) and the raw Messages API (halo_format_claude.raw — create_raw_halo, no Agent SDK needed). Tool results become a shape map kept out of context.

MagAgent — CLI AI coding agent with persistent MagGraph memory. Like the Magpie: intelligent, tool-using, and never forgets.

Managed Deep Agents — the define_deep_agent authoring interface plus the CLI that compiles and deploys a code-first Deep Agent repository to a managed LangGraph runtime.

Compatibility installer for MothX. Use the mothx-installer package for future updates.

AI coding assistant in the terminal

Autonomous AI coding agent

AI-powered vibe coder, live debugger, and agent session manager — supports OpenAI, Anthropic, and Google Gemini

GSD Pi local-first coding agent

TypeScript SDK that provides a unified API for working with multiple LLM providers, automatic model discovery, and more.

Indusagi — a terminal-first AI coding agent framework. Clean-room implementation.

AIACA — AI Agentic Coding Assistant. A production-grade agentic CLI with multi-provider support (Gemini, Claude, OpenRouter, Cerebras, Groq, Hugging Face), rich TUI, and 100+ tools.

Code-native agentic runtime for TypeScript.

MCP-first infrastructure & agentic-AI cartography — install once, every AI agent knows your system landscape. Read-only discovery exposed over the Model Context Protocol.

Agentic development framework — multi-runtime support for 19 AI runtimes (Claude Code, OpenCode, Codex, Kiro + 15 rules-based editors)

SharedLLM CLI — route agentic coding tools (Claude Code, etc.) through the SharedLLM gateway

Cross-platform installer for the curated ₹0 awesome-agentic-stack developer workspace.

Zero-code auto-instrumentation for AI agents. Detects and traces LangChain, CrewAI, AutoGen, OpenAI, Anthropic, and raw HTTP calls automatically.

Small, reviewable, validation-gated agent skills for Codex-style project work.

Generate, preserve, and verify lean repo context for AI coding agents

Python SDK for controlling visible ChatGPT Chat and Work through a local backend.

Halo host adapter for LangChain agents and LangGraph graphs (Python): a wrap_tool_call encode middleware plus a halo_fetch navigation tool. install_halo() wires it in one call.

Connect with Claude Code, Codex CLI, and Gemini CLI — a local prompt timeline with AI-powered prompt enhancement and revision.

MyAI Local Agent — connects your machine to the MyAI cloud AI coding assistant

Solo Founder OS agent #11 — overdue invoice reminders with HITL gating. Stripe-shaped types; works with or without a Stripe key (mock provider for dev/dry-run).

Curses picker for resuming Claude Code sessions

REF Agents — AI-powered SDLC governance for the Relay Engineering Framework. 19 expert personas enforcing quality gates via Model Context Protocol (MCP).

MCP wrapper for controlling Codex app-server threads, turns, plan mode, and steering.

VibeBot review: compare features, pricing, use cases, access model, and alternatives for this AI Agents Platform agent in 2026. A no-code AI platform for creating Discord bots.

AI agent that implements your specs, opens PRs, and reviews code overnight. Queue GitHub issues or PRDs, wake up to pull requests.

Single-agent terminal AI engineering runtime with full tools, direct execution, and clean UX.

Grawkus — terminal coding agents with a mind for the whole repo. Speaks any OpenAI-compatible API with repo-aware context, benchmark tracing, MemPalace memory, and terminal-first agent workflows.

TyCode — AI system agent with a TUI that works with any LLM provider

Autonomous AI coding agent that orchestrates 26+ skills via OpenClaw — thin runtime over the clawpowers capability library

Autonomous agent runtime for Claude Code — installs slash commands, safety hooks, and multi-agent task execution

Portable, vendor-neutral AI Dev OS for multi-agent coding workflows

Interactive developer CLI for WAMA (WhatsApp Multi-Agent) to manage instances, link accounts, poll QR codes, send messages, and query logs.

Comprehensive, high-performance, and safety-hardened Pi-native multi-agent orchestration package, featuring advanced workflows, damage-control rules, and developer tooling.

npm for your coding agent. Install packs of skills, subagents, and hooks into any repo, for every major agent.

A hierarchical multi-agent harness that autonomously audits a codebase, finds high-value improvements, and applies them in TDD-gated iterations.

Give Claude total recall of its own un-compacted conversation — extract, search, and recall Claude Code transcripts.

Universal agent server. Wraps any LangGraph graph and exposes it over standard agent protocols — Vercel AI SDK, Claude Code, TUIs, and more.

Islo (islo.dev) sandbox integration for Deep Agents

MCP server giving AI agents controlled GitHub access with policy guard and audit trail

Update all your AI agent CLIs and skills concurrently

Centralized AI agent rules for Cursor, Claude Code, Codex, and Copilot